Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1077 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1053212 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3628. Min Act: -0.0000

Data Index: 39530 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3022. Min Act: -0.0000

Data Index: 298403 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3163. Min Act: -0.0000

Data Index: 865099 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3273. Min Act: -0.0000

Data Index: 106690 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3205. Min Act: -0.0000

Data Index: 580247 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3040. Min Act: -0.0000

Data Index: 58475 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2875. Min Act: -0.0000

Data Index: 654411 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3105. Min Act: -0.0000

Data Index: 9842 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1265324 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2884. Min Act: -0.0000

Data Index: 78168 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3138. Min Act: -0.0000

Data Index: 697603 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1206253 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2982. Min Act: -0.0000

Data Index: 501986 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1130315 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1310468 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2736. Min Act: -0.0000

Data Index: 618473 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2863. Min Act: -0.0000

Data Index: 917268 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2939. Min Act: -0.0000

Data Index: 267735 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2976. Min Act: -0.0000

Data Index: 275883 (C4 (Web Text))

Max Activating Token Index: 587